HaozhiQi / RPIN
Learning Long-term Visual Dynamics with Region Proposal Interaction Networks (ICLR 2021)
☆112Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for RPIN
- CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning☆103Updated 3 years ago
- Video Noise Contrastive Estimation☆65Updated last year
- [ICLR 2019] ]Unsupervised Discovery of Parts, Structure, and Dynamics☆46Updated last year
- Official Release of ICLR 2020 paper "SCALOR: Generative World Models with Scalable Object Representations"☆48Updated 10 months ago
- Learning Spatial Common Sense with Geometry-Aware Recurrent Networks☆55Updated 4 years ago
- Neural Networks that convert input movies into Physical Scene Graphs (PSGs)☆62Updated 3 years ago
- An implementation of the MONet model for unsupervised scene decomposition in PyTorch☆58Updated 2 years ago
- Burgess et al. "MONet: Unsupervised Scene Decomposition and Representation"☆89Updated last year
- Official PyTorch implementation of "Improving Generative Imagination in Object-Centric World Models"☆34Updated last year
- Official PyTorch implementation of "SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition"☆101Updated last year
- Unsupervised learning of Object Landmarks through Conditional Image Generation☆47Updated 4 years ago
- Official PyTorch implementation of GENESIS and GENESIS-V2☆97Updated 2 years ago
- EfficientMORL (ICML'21)☆22Updated 3 years ago
- Learning interaction hotspots from egocentric video☆48Updated last year
- Code, data and benchmark from the paper "Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences".☆36Updated 3 years ago
- Code accompanying EGO-TOPO: Environment Affordances from Egocentric Video (CVPR 2020)☆29Updated 2 years ago
- Learning about objects and their properties by interacting with them☆12Updated 4 years ago
- PyTorch re-implementation of Multi-Object Representation Learning with Iterative Variational Inference☆58Updated 2 years ago
- ☆39Updated 9 months ago
- Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies☆107Updated last year
- Code for unsupervised learning of object landmarks as proposed in "Unsupervised Learning of Object Landmarks through Conditional Image Ge…☆149Updated 5 years ago
- Use the Force Luke! Learning to Predict Physical Forces by Simulating Effects [CVPR2020] (https://arxiv.org/pdf/2003.12045.pdf)☆72Updated last year
- ☆27Updated 5 years ago
- Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation (ECCV 2020)☆33Updated last year
- A set of neural network modules, which are small fully connected layers operating in semantic concept space. These modules are configured…☆58Updated 3 years ago
- [NeurIPS 2021 Spotlight] Learning to Compose Visual Relations☆101Updated last year
- "CoPhy: Counterfactual Learning of Physical Dynamics", F. Baradel, N. Neverova, J. Mille, G. Mori, C. Wolf, ICLR'2020☆33Updated 4 years ago
- [CVPR 2019] Connecting Touch and Vision via Cross-Modal Prediction☆70Updated 5 years ago
- ☆50Updated 6 years ago